QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games
Neurocomputing（2008）
摘要
Markov games is a framework which can be used to formalise n-agent reinforcement learning (RL). Littman (Markov games as a framework for multi-agent reinforcement learning, in: Proceedings of the 11th International Conference on Machine Learning (ICML-94), 1994.) uses this framework to model two-agent zero-sum problems and, within this context, proposes the minimax-Q algorithm. This paper reviews RL algorithms for two-player zero-sum Markov games and introduces a new, simple, fast, algorithm, called QL"2. QL"2 is compared to several standard algorithms (Q-learning, Minimax and minimax-Q) implemented with the Qash library written in Python. The experiments show that QL"2 converges empirically to optimal mixed policies, as minimax-Q, but uses a surprisingly simple and cheap updating rule.
更多查看译文
关键词
simple reinforcement,reinforcement learning,two-agent zero-sum problem,minimax-q algorithm,multi-agent,q -learning,multi-agent reinforcement learning,international conference,two-player zero-sum games,markov games,reinforcement learning q -learning markov games two-player zero-sum games multi-agent,n-agent reinforcement learning,standard algorithm,machine learning,markov game,rl algorithm,two-player zero-sum markov game,q,q learning,zero sum game
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要